© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48296
    Prev
    Next
    INDEX
    Explanations

    friendship and support networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keten
    -1.29
     traditionelle
    -1.21
     molle
    -1.19
     nasional
    -1.15
    Meanwhile
    -1.15
     gelar
    -1.13
    vaní
    -1.13
    هه
    -1.13
     стоимости
    -1.10
     jahre
    -1.09
    POSITIVE LOGITS
    řízení
    1.42
     support
    1.27
    čku
    1.25
     didn
    1.23
    がございます
    1.21
    IntentFilter
    1.21
    纾
    1.20
     see
    1.19
    řízen
    1.19
     "..\..\
    1.18
    Activations Density 0.062%

    No Known Activations